Re:Building an early warning system for LLM-aided biological...
by danielmarkbruce on Wednesday January 31, 2024 @05:22PM
(#39210262)
with GPT-4 (non-turbo) and a good system prompt?
[ Parent
| on HN ]
Re:Building an early warning system for LLM-aided biological...
by sjwhevvvvvsj on Wednesday January 31, 2024 @08:45PM
(#39211944)
It’s unpredictable, usually it behaves but on arbitrary web text you’ll eventually trigger a “safety” barrier, and sometimes just trying again will work.